Functional network integration and attention skills in young children

Abstract

Children acquire attention skills rapidly during early childhood as their brains undergo vast neural development. Attention is well studied in the adult brain, yet due to the challenges associated with scanning young children, investigations in early childhood are sparse. Here, we examined the relationship between age, attention and functional connectivity (FC) during passive viewing in multiple intrinsic connectivity networks (ICNs) in 60 typically developing girls between 4 and 7 years whose sustained, selective and executive attention skills were assessed. Visual, auditory, sensorimotor, default mode (DMN), dorsal attention (DAN), ventral attention (VAN), salience, and frontoparietal ICNs were identified via Independent Component Analysis and subjected to a dual regression. Individual spatial maps were regressed against age and attention skills, controlling for age. All ICNs except the VAN showed regions of increasing FC with age. Attention skills were associated with FC in distinct networks after controlling for age: selective attention positively related to FC in the DAN; sustained attention positively related to FC in visual and auditory ICNs; and executive attention positively related to FC in the DMN and visual ICN. These findings suggest distributed network integration across this age range and highlight how multiple ICNs contribute to attention skills in early childhood.

Keywords: Attention; Children; Early childhood; Functional connectivity; ICA; Neural networks.

Fig. 1

Average FD timecourse across participants for mean relative displacement before and after denoising in black and green respectively, is depicted in panel (a). Panel (b) shows an example of a low-motion scan before and after denoising, while panel (c) shows an example of a high-motion scan before and after denoising. No participants showed FD spikes >0.3 mm after denoising.

Fig. 2

Sensory and cognitive networks of interest were extracted from the children’s cleaned passive viewing fMRI data via Independent Component Analysis (ICA). Network maps were thresholded at Z > 3.1 and projected onto surfaces in SUMA for visualization purposes. The following are shown in radiological convention: (a) primary visual network, (b) primary auditory network, (c) sensorimotor network, (d) anterior default mode network, (e) posterior default mode network, (f) right frontoparietal network, (g) salience network with the anterior insula circled in red, (h) ventral attention network, (i) inferior dorsal attention network, and (j) superior dorsal attention network. The average FC for each network is depicted in panel (k), ordered from highest to lowest.

Fig. 3

Associations with age in sensory and cognitive networks. Participant-specific versions of the spatial maps and associated timeseries were generated using FSL’s dual regression approach and associations with age within each ICN were assessed using FSL’s Randomise with p < 0.05 corrected for multiple comparisons while controlling for handedness and IQ. Positive associations with age were found in the (a) primary visual network, (b) primary auditory network, (c) sensorimotor network, (d) anterior default mode network, (e) posterior default mode network, (f) right frontoparietal network, (g) salience network, (h) inferior dorsal attention network, and (i) superior dorsal attention network. Significant associations with age are depicted in the red overlay; the yellow underlay depicts the respective network. Age is given in years (mean-centered); FC values are parameter estimates (β) in arbitrary units (mean-centered). DAN = dorsal attention network; DMN = default mode network; FP.

Fig. 4

Associations with sustained, selective and executive attention in sensory and cognitive networks. Participant-specific version of the spatial maps and associated timeseries were generated using FSL’s dual regression approach and associations with attention within each ICN were assessed using FSL’s Randomise with p < 0.05 corrected for multiple comparisons while controlling for age in addition to handedness and IQ. Positive associations with sustained attention were found in the (a) primary visual network and the (b) primary auditory network; with selective attention in the (c) inferior dorsal attention network; and for executive attention in the (d) primary visual network, as well as the (e) anterior default mode network. Significant associations with attention are depicted in the red overlay; the yellow underlay depicts the respective network. Attention is given as score on the respective task (mean-centered); FC values are parameter estimates (β) in arbitrary units (mean-centered). DAN = dorsal attention network; DMN = default mode network.